© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 86984
    Prev
    Next
    INDEX
    Explanations

    preseason games and practice

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_10/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     när
    -1.91
        
    -1.84
    hemp
    -1.76
     wanneer
    -1.72
    犼
    -1.68
    ⟝
    -1.68
    髣
    -1.66
    AUD
    -1.63
    那时
    -1.63
     cuando
    -1.62
    POSITIVE LOGITS
    ing
    1.92
    曏
    1.73
    ers
    1.70
     acheteurs
    1.64
    樘
    1.61
    ;.
    1.59
     regardé
    1.59
     spectateurs
    1.59
    ."
    1.57
    箆
    1.55
    Activations Density 0.009%

    No Known Activations